Research on fault diagnosis of time-domain vibration signal based on convolutional neural networks
In order to maintain the safe operation of various types of equipment, the health status of main components should be monitored in real-time, and the demand for intelligent fault diagnosis algorithm has increased sharply. However, the traditional intelligent diagnosis algorithm is based on the manua...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2019-12-01
|
| Series: | Systems Science & Control Engineering |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/21642583.2019.1661311 |
| _version_ | 1828398388385677312 |
|---|---|
| author | Mingyong Li Qingmin Wei Hongya Wang Xuekang Zhang |
| author_facet | Mingyong Li Qingmin Wei Hongya Wang Xuekang Zhang |
| author_sort | Mingyong Li |
| collection | DOAJ |
| description | In order to maintain the safe operation of various types of equipment, the health status of main components should be monitored in real-time, and the demand for intelligent fault diagnosis algorithm has increased sharply. However, the traditional intelligent diagnosis algorithm is based on the manual method for signal feature extraction, which has high requirements for expert experience and poor generality. A convolutional neural network, with big data as its engine, is the most effective pattern classification algorithm at present. In this paper, the convolutional neural network is applied to time-domain vibration signal fault diagnosis, taking the bearing as an example, and an intelligent diagnosis method of bearing based on convolution neural network is proposed. The proposed method does not need manual feature extraction, and can automatically complete feature extraction and automatic fault recognition. The convolutional neural network has three convolutional layers. We use data enhancement techniques for the input raw signal and convert the one-dimensional original time-domain vibration signal into a two-dimensional signal. The model shows good results on CWRU dataset and the recognition accuracy of the algorithm in the CWRU bearing database is more than 96%. |
| first_indexed | 2024-12-10T09:00:41Z |
| format | Article |
| id | doaj.art-6071f357546642f6b66e7fd55b4e3426 |
| institution | Directory Open Access Journal |
| issn | 2164-2583 |
| language | English |
| last_indexed | 2024-12-10T09:00:41Z |
| publishDate | 2019-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Systems Science & Control Engineering |
| spelling | doaj.art-6071f357546642f6b66e7fd55b4e34262022-12-22T01:55:18ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832019-12-0173738110.1080/21642583.2019.16613111661311Research on fault diagnosis of time-domain vibration signal based on convolutional neural networksMingyong Li0Qingmin Wei1Hongya Wang2Xuekang Zhang3Donghua UniversityChongqing Normal UniversityDonghua UniversityDonghua UniversityIn order to maintain the safe operation of various types of equipment, the health status of main components should be monitored in real-time, and the demand for intelligent fault diagnosis algorithm has increased sharply. However, the traditional intelligent diagnosis algorithm is based on the manual method for signal feature extraction, which has high requirements for expert experience and poor generality. A convolutional neural network, with big data as its engine, is the most effective pattern classification algorithm at present. In this paper, the convolutional neural network is applied to time-domain vibration signal fault diagnosis, taking the bearing as an example, and an intelligent diagnosis method of bearing based on convolution neural network is proposed. The proposed method does not need manual feature extraction, and can automatically complete feature extraction and automatic fault recognition. The convolutional neural network has three convolutional layers. We use data enhancement techniques for the input raw signal and convert the one-dimensional original time-domain vibration signal into a two-dimensional signal. The model shows good results on CWRU dataset and the recognition accuracy of the algorithm in the CWRU bearing database is more than 96%.http://dx.doi.org/10.1080/21642583.2019.1661311Convolutional neural networktime-domain vibration signalfault diagnosismachine learning |
| spellingShingle | Mingyong Li Qingmin Wei Hongya Wang Xuekang Zhang Research on fault diagnosis of time-domain vibration signal based on convolutional neural networks Systems Science & Control Engineering Convolutional neural network time-domain vibration signal fault diagnosis machine learning |
| title | Research on fault diagnosis of time-domain vibration signal based on convolutional neural networks |
| title_full | Research on fault diagnosis of time-domain vibration signal based on convolutional neural networks |
| title_fullStr | Research on fault diagnosis of time-domain vibration signal based on convolutional neural networks |
| title_full_unstemmed | Research on fault diagnosis of time-domain vibration signal based on convolutional neural networks |
| title_short | Research on fault diagnosis of time-domain vibration signal based on convolutional neural networks |
| title_sort | research on fault diagnosis of time domain vibration signal based on convolutional neural networks |
| topic | Convolutional neural network time-domain vibration signal fault diagnosis machine learning |
| url | http://dx.doi.org/10.1080/21642583.2019.1661311 |
| work_keys_str_mv | AT mingyongli researchonfaultdiagnosisoftimedomainvibrationsignalbasedonconvolutionalneuralnetworks AT qingminwei researchonfaultdiagnosisoftimedomainvibrationsignalbasedonconvolutionalneuralnetworks AT hongyawang researchonfaultdiagnosisoftimedomainvibrationsignalbasedonconvolutionalneuralnetworks AT xuekangzhang researchonfaultdiagnosisoftimedomainvibrationsignalbasedonconvolutionalneuralnetworks |